© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 64149
    Prev
    Next
    INDEX
    Explanations

    out to, weigh their, outlined in, foundations of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    åĽ½æ°ij
    -0.11
    èĬĴ
    -0.09
    ä¸įåIJĪ
    -0.09
    éĢIJ
    -0.09
    âĹī
    -0.08
    ä¸Ĭ线
    -0.08
    ä¸įå½ĵ
    -0.08
    èĴ¸
    -0.08
    çļ´
    -0.08
    åĨĮ
    -0.08
    POSITIVE LOGITS
    讽åĪº
    0.11
    éĩİå¿ĥ
    0.08
    bat
    0.08
     ngữ
    0.08
    æľĢ主è¦ģ
    0.08
    rant
    0.08
    éĩijèŀįåį±æľº
    0.08
    LOB
    0.08
    éļIJ约
    0.08
    åIJ¹
    0.08
    Activations Density 0.769%

    No Known Activations